Hybrid Direct Neural Network Controller With Linear Feedback Compensator

In this paper Hybrid Direct Neural Controller (HDNC) with Linear Feedback Compensator (LFBC) has been developed. Proper initialization of neural network weights is a critical problem. This paper presents two different neural network configurations with unity and random weight initialization while using it as a direct controller and linear feedback compensator. The performances of these controller configurations are demonstrated on the two different applications i.e. Continues Stirred Tank Reactor as nonlinear and DC Motor as linear. In this work a direct neural control strategy with linear feedback compensator is used to control the process. Error back propagation algorithm based on gradient algorithm is used to minimize the error between the plant output and desired output signal. The Direct Neural Controller (DNC) and Hybrid Direct Neural Controller (HDNC) are compared in terms of the Integral Square Error (ISE) and Integral Absolute Error (IAE). Addition of a linear feedback compensator helps to improve both the transient as well as steady state response of the system